Updated: Dec 10, 2025
base model
This page contains fp8 quantized DiT models of Neta Lumina for ComfyUI.
Neta Lumina (NT)
NetaYume Lumina (NTYM)
And a fp8 quantized Gemma 2 2b (the text encoder).
All credit belongs to the original model author. License is the same as the original model.
Update (11/27/2025): mixed precision and fp8 tensor core support (mptc).
This is a new ComfyUI feature that supports fp8 tensor core, also with mixed precision.
In short:
Mixed precision: Keep important layers in BF16.
FP8 tensor core support: On supported GPU, much faster (30~80%) than BF16 and classic FP8 scaled models. Because ComfyUI will do calculations in FP8 directly, instead of dequantizing + BF16. torch.compile is recommended.
More info: https://civitai.com/models/2172944/z-image-turbo-tensorcorefp8